System and method for generating implicit ratings using user-generated content

Abstract

A system and method for generating implicit ratings using user generated content. A web and social media scraper collect and preprocesses online user generated content for ingestion by machine learning classifiers that provide a confidence score relating to the sentiment of a product. That score is then normalized to the requested score level and compared against a threshold subsequently determining the product's implicit rating. Explicit ratings may further inform the rating calculations to produce more accurate ratings or combined ratings.

What is claimed is: 
     
         1 . A system for generating implicit ratings using user generated content, comprising:
 a computer system comprising a memory and a processor;   a rating system application programming interface comprising a first plurality of programming instructions stored in the memory and operating on the processor, wherein the first plurality of programming instructions, when operating on the processor, causes the computer system to:
 receive a request for an implicit rating, wherein the request comprises a product or service to be rated and a rating normalization factor; and 
 send the request to a web and social media scraper; 
   a web and social media scraper comprising a second plurality of programming instructions stored in the memory and operating on the processor, wherein the second plurality of programming instructions, when operating on the processor, causes the computer system to:
 retrieve data comprising user generated content relating to the product or service; 
 preprocess the data, wherein preprocessing prepares data for ingestion by a machine learning classifier; and 
 send the preprocessed data to a machine learning engine; and 
   a machine learning engine comprising a third plurality of programming instructions stored in the memory and operating on the processor, wherein the third plurality of programming instructions, when operating on the processor, causes the computer system to:
 analyze the preprocessed data for sentiment relating to the product or service; 
 produce a confidence score, wherein the confidence score is a percentage of confidence from the machine learning classifier relating to the sentiment of the user generated content towards the product or service; 
 sum all the confidence scores from each one of the user generated content; 
 convert the summed confidence score to a rating, wherein the percentage of the confidence score equates to a specific number of rating units; 
 normalize the rating using the rating normalization factor; and 
 return the normalized rating to the origin of the request. 
   
     
     
         2 . The system of  claim 1 , further comprising a database, wherein the database stores implicit ratings for use upon request. 
     
     
         3 . The system of  claim 1 , wherein the machine learning engine comprises a machine learning classifier selected from the list comprising of natural language processing, computer vision, and facial recognition. 
     
     
         4 . The system of  claim 1 , wherein the web and social media scraper further comprises machine learning classifiers designed to identify the requested product or service in user generated content. 
     
     
         5 . A method for generating implicit ratings using user generated content, comprising the steps of:
 receiving a request for an implicit rating, wherein the request comprises a product or service to be rated and a rating normalization factor;   retrieving data comprising user generated content relating to the product or service;   preprocess the data, wherein preprocessing prepares data for ingestion by a machine learning classifier;   analyzing the preprocessed data for sentiment relating to the product or service;   producing a confidence score, wherein the confidence score is a percentage of confidence from the machine learning classifier relating to the sentiment of the user generated content towards the product or service;   summing all the confidence scores from each one of the user generated content;   converting the summed confidence score to a rating, wherein the percentage of the confidence score equates to a specific number of rating units;   normalizing the rating using the rating normalization factor; and   returning the normalized rating to the origin of the request.   
     
     
         6 . The method of  claim 5 , further comprising a database, wherein the database stores implicit ratings for use upon request. 
     
     
         7 . The method of  claim 5 , wherein the machine learning engine comprises a machine learning classifier selected from the list comprising of natural language processing, computer vision, and facial recognition. 
     
     
         8 . The method of  claim 5 , wherein the web and social media scraper further comprises machine learning classifiers designed to identify the requested product or service in user generated content.